Empirical analysis of the effect of dimension reduction and word order on semantic vectors

Sitbon, Laurianne, Bruza, Peter D., & Prokopp, Christian Werner (2012) Empirical analysis of the effect of dimension reduction and word order on semantic vectors. International Journal of Semantic Computing, 6(3), pp. 329-351.

View at publisher


The aim of this paper is to provide a comparison of various algorithms and parameters to build reduced semantic spaces. The effect of dimension reduction, the stability of the representation and the effect of word order are examined in the context of the five algorithms bearing on semantic vectors: Random projection (RP), singular value decom- position (SVD), non-negative matrix factorization (NMF), permutations and holographic reduced representations (HRR). The quality of semantic representation was tested by means of synonym finding task using the TOEFL test on the TASA corpus. Dimension reduction was found to improve the quality of semantic representation but it is hard to find the optimal parameter settings. Even though dimension reduction by RP was found to be more generally applicable than SVD, the semantic vectors produced by RP are somewhat unstable. The effect of encoding word order into the semantic vector representation via HRR did not lead to any increase in scores over vectors constructed from word co-occurrence in context information. In this regard, very small context windows resulted in better semantic vectors for the TOEFL test.

Impact and interest:

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

121 since deposited on 07 Jan 2013
8 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 56106
Item Type: Journal Article
Refereed: Yes
Keywords: Semantic spaces, Holographic Reduced Representation, SVD, Non-negative matrix factorization, Random Indexing
DOI: 10.1142/S1793351X12500055
ISSN: 1793-7108
Subjects: Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Natural Language Processing (080107)
Divisions: Current > Schools > School of Electrical Engineering & Computer Science
Current > Schools > School of Information Systems
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Copyright 2012 World Scientific Publishing
Deposited On: 07 Jan 2013 01:07
Last Modified: 19 Feb 2013 00:44

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page